Command Splitting for High-Cost Data Access Operations

1. A method comprising: receiving a data access command targeting a logical block address (LBA) extent in a storage device; determining that execution of the data access command includes moving a read/write head across an identified high-performance-cost boundary, the high-performance cost boundary being between two logically-ordered data blocks for which sequential write access causes the storage device to incur a delay in excess of a predetermined delay threshold; splitting the data access command into two or more separate data access commands responsive to the determination; determining an execution order for the data access commands based on at least one performance-efficiency consideration; separately queuing the data access commands in memory for execution according to the determined execution order; and controlling the read/write, head to execute each of the queued data access commands.

2. The method of claim 1 , wherein splitting the data access command into the two or more separate data access commands includes splitting the LBA extent at the identified high-performance-cost boundary and generating a first data access command to write data blocks associated with a first side of the identified high-performance-cost boundary and a second data access command to write data blocks associated with a second opposite side of the identified high-performance-cost boundary.

3. The method of claim 1 , wherein the execution order is determined based on write/read settings associated with targeted physical blocks, the execution order mitigating a number of interlayer seeks.

4. The method of claim 1 , wherein the execution order is determined based on positions of targeted physical blocks, the execution order mitigating total seek times observed during execution of a plurality of commands in the queued sequence.

5. The method of claim 1 , wherein the high-performance-cost boundary is a logical boundary between two logical blocks corresponding to non-consecutive physical data blocks.

6. The method of claim 5 , wherein one of the non-consecutive physical data blocks was initially a spare data block that was mapped to one of the two logical blocks responsive to detection of a defective physical data block.

7. The method of claim 1 , wherein the identified high-performance-cost boundary is a logical boundary between two blocks corresponding to data tracks of different written track width.

8. A storage device comprising: a storage medium; a controller executable to: receive a data access command targeting an LBA extent; determine that execution of the data access command includes moving a read/write head across an identified high-performance-cost boundary, the high-performance cost boundary being between two logically-ordered data blocks for which sequential write access causes the storage device to incur a delay in excess of a predetermined delay threshold; split the data access command into two data access commands each associated with logical blocks on an opposite side of the identified high-performance-cost boundary responsive to the determination; determine an execution order for the two data access commands based on at least one performance-efficiency consideration, separately queue the two data access commands in memory for execution according to the determined execution order; and control the read/write head to execute each of the two queued data access commands.

9. The storage device of claim 8 , wherein the controller determines the execution order based on write/read settings associated with targeted physical blocks, the execution order mitigating a number of interlayer seeks.

10. The storage device of claim 8 , wherein the controller determines the execution order based on positions of targeted physical blocks, the execution order mitigating total seek times observed during execution of a plurality of commands in the queued sequence.

11. The storage device of claim 8 , wherein the identified high-performance-cost boundary is a logical boundary between two logical blocks corresponding to non-consecutive physical data blocks.

12. The storage device of claim 11 , wherein one of the non-consecutive physical data blocks was initially a spare data block that was mapped to one of the two logical blocks responsive to detection of a defective-physical data block.

13. The storage device of claim 8 , wherein the identified high-performance-cost boundary is a logical boundary between two blocks corresponding to data tracks of different written track width.

14. One or more computer-readable storage media of a tangible article of manufacture encoding computer-executable instructions for executing on a computer system a computer process comprising: receiving a data access command targeting an LBA extent in a storage device; determining that execution of the data access command includes moving a read/write head across an identified high-performance-cost boundary, the high-performance cost boundary being between two logically-ordered data blocks for which sequential write access causes the storage device to incur a delay in excess of a predetermined delay threshold; splitting the data access command into two or more separate data access commands responsive to the determination; determining an execution order for the two or more separate data access commands based on at least one performance-efficiency consideration separately queuing the two or more separate data access commands in memory for execution according to the determined execution order; and controlling the read/write head to execute each of the queued data access commands.

15. The one or more computer-readable storage media of claim 14 , wherein splitting the data access command into the two or more separate data access commands includes splitting the LBA extent at the identified high-performance-cost boundary and generating a first data access command to write data blocks associated with a first side of the identified high-performance-cost boundary and a second data access command to write data blocks associated with a second opposite side of the identified high-performance-cost, boundary.

16. The one or more computer-readable storage media method of claim 14 , wherein the execution order is determined based on positions of targeted physical blocks, the execution order mitigating total seek times observed during execution of a plurality of commands in the queued sequence.

17. The one or more computer-readable storage media method of claim 14 , wherein the execution order is determined based on write/read settings associated with targeted physical blocks, the execution order mitigating a number of interlayer seeks.